SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.01232 · AAAI · 2024

Motif-Aware Riemannian Graph Neural Network with Generative-Contrastive Learning

Hao Peng, Philip Yu, Sun Li, Zixi Wang, Zhenhao Huang, Feiyang Wang

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2401.01232.json · badge: /api/ran/2401.01232.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
riemanngraph/motifrgc marked official in Papers with Code
Papers with Code archive
4 ran · 2 no recorded run
FunctionStatusWhere it lives
FermiDiracDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
riemanngraph/motifrgc/models.py
code served (permissive licence) · get_code("0d4dfceee7018e3d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, FermiDiracDecoder: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# FermiDiracDecoder takes r and t as parameters
# Looking at the forward method, it uses:
# - self.r: a scalar value used in arithmetic with dist
# - self.t: a scalar value used in arithmetic with dist
# - dist: a tensor passed to forward

# Create small scalar values for r and t
r = 0.5
t = 0.1

# Create a small distance tensor for testing
dist = torch.randn(2, 4)

ARGS = {
    "r": r,
    "t": t,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FermiDiracDecoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a FermiDiracDecoder output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
GAT Ran
ran on a synthesized input · constructed an object; no result was computed
riemanngraph/motifrgc/models.py
code served (permissive licence) · get_code("cbb8804ff702cf89")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, GAT: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch_geometric.nn import GATConv

torch.manual_seed(0)

ARGS = {
    "n_layers": 3,
    "in_features": 4,
    "hidden_features": 8,
    "out_features": 3,
    "heads": 2,
    "drop_edge": 0.5,
    "drop_feats": 0.5,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GAT — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GAT output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
GCN Ran
ran on a synthesized input · constructed an object; no result was computed
riemanngraph/motifrgc/models.py
code served (permissive licence) · get_code("edd81c40e27d23fc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, GCN: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch_geometric.data import Data

torch.manual_seed(0)

# Create minimal valid arguments
n_layers = 3
in_features = 4
hidden_features = 8
out_features = 2
drop_edge = 0.5
drop_feats = 0.5

# Create a small graph with 2 nodes and minimal edges
x = torch.randn(2, in_features)
edge_index = torch.tensor([[0, 1], [1, 0]], dtype=torch.long).t().contiguous()

ARGS = {
    "n_layers": n_layers,
    "in_features": in_features,
    "hidden_features": hidden_features,
    "out_features": out_features,
    "drop_edge": drop_edge,
    "drop_feats": drop_feats,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GCN — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GCN output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
GraphSAGE Ran
ran on a synthesized input · constructed an object; no result was computed
riemanngraph/motifrgc/models.py
code served (permissive licence) · get_code("f419f73bc3b2cfe8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, GraphSAGE: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch_geometric.data import Data

torch.manual_seed(0)

# Create small tensors for a toy graph
n_nodes = 2
in_features = 4
hidden_features = 3
out_features = 5

# Node features: (n_nodes, in_features)
x = torch.randn(n_nodes, in_features)

# Edge index: (2, n_edges) - simple edge list
edge_index = torch.tensor([[0, 1], [1, 0]], dtype=torch.long).t().contiguous()

ARGS = {
    "n_layers": 3,
    "in_features": in_features,
    "hidden_features": hidden_features,
    "out_features": out_features,
    "drop_edge": 0.5,
    "drop_feats": 0.5,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GraphSAGE — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GraphSAGE output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
Model Not yet run
unverified (harvested, no recorded run)
riemanngraph/motifrgc/models.py
code served (permissive licence) · get_code("c426aa4122c719cd")
How it ran

no invocation recorded.

RiemannianFeatures Not yet run
unverified (harvested, no recorded run)
riemanngraph/motifrgc/models.py
code served (permissive licence) · get_code("e88ac555d2d0018a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Graphs are typical non-Euclidean data of complex structures. In recent years, Riemannian graph representation learning has emerged as an exciting alternative to Euclidean ones. However, Riemannian methods are still in an early stage: most of them present a single curvature (radius) regardless of structural complexity, suffer from numerical instability due to the exponential/logarithmic map, and lack the ability to capture motif regularity. In light of the issues above, we propose the problem of Motif-aware Riemannian Graph Representation Learning, seeking a numerically stable encoder to capture motif regularity in a diverse-curvature manifold without labels. To this end, we present a novel Motif-aware Riemannian model with Generative-Contrastive learning (Mo-tifRGC), which conducts a minmax game in Riemannian manifold in a self-supervised manner. First, we propose a new type of Riemannian GCN (D-GCN), in which we construct a diverse-curvature manifold by a product layer with the diversified factor, and replace the exponential/logarithmic map by a stable kernel layer. Second, we introduce a motif-aware Riemannian generative-contrastive learning to capture motif regularity in the constructed manifold and learn motif-aware node representation without external labels. Empirical results show the superiority of MofitRGC.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.01232")
get_code_for_paper("2401.01232")
have("2401.01232")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2401.01232.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2401.01232.svg)](https://syntology.ai/paper/2401.01232)

Connect an agent — have() is free.